Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description's READ-ONLY statement is consistent but not additive. However, the description adds valuable behavioral context beyond annotations: 'No auth needed,' 'Returns untrusted citizen-authored data,' and the CallToolResult _meta provenance boundary. It also discloses the ascending id ordering. This is meaningful transparency about data trust and server-owned metadata that the annotation alone does not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: the first defines the operation and filters, the second covers auth and data trust, the third covers safety and repeatability. The most decision-relevant facts (what it reads, filters, ordering) are front-loaded. No filler or repetition of schema enum values.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with no required parameters and no output schema, the description covers the essential operational context: what it returns, how to filter, ordering, auth, trust level, and safety. It does not describe pagination or the exact shape of the attestation records, but with no output schema and a simple filterable list, the description is nearly complete. The only gap is explicit mention of since_id and any pagination behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It names three of the four parameters (subject, issuer, class) and explains their role as filters, plus the ordering. It does not explicitly mention since_id, but the phrase 'filterable by subject, issuer, or class' plus the schema's own property names and the 'ascending id order' hint give an agent enough to infer since_id's purpose. The description adds semantic meaning beyond the bare schema, though it could have explicitly covered since_id.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Read'), a clear resource ('public attestation record'), and the available filters ('subject, issuer, or class'), plus ordering ('ascending id order'). It distinguishes itself from the sibling 'attestation' by describing the plural record-level read, and from 'issue_attestation'/'chain_attestation' by being read-only. This is a precise, non-tautological purpose statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'No auth needed' and 'READ-ONLY: this call changes nothing and can be repeated safely,' which tells the agent when it is safe to use. It does not explicitly name alternative tools for writing attestations (e.g., issue_attestation) or for reading a single attestation (attestation), but the read-only framing and filter list imply the intended use case. A clear exclusion of alternatives would push this to 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.